INDEX

Explanations

sections of code or structured data related to web or document elements

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

InjectAttribute

-0.92

 désolés

-0.71

EndProject

-0.70

LookAnd

-0.68

basicConfig

-0.66

argout

-0.61

CppMethod

-0.60

mybatisplus

-0.60

MemoryWarning

-0.60

Rüyada

-0.59

POSITIVE LOGITS

جغرافيا

0.65

ainville

0.60

 Haarlem

0.58

ividual

0.57

sonian

0.57

 Conſ

0.56

 depositphotos

0.56

 poiv

0.56

 Monfieur

0.55

 Kalt

0.55

Activations Density 0.055%

sections of code or structured data related to web or document elements

No Comments

No Known Activations